Recall the filter between the AI and the world. The AI doesn’t directly say “yes/no.” The AI gives a proof to the filter which then says either “yes, the AI found a proof” or “no, the AI didn’t.” So they do all say ‘yes’ if they can. I will modify the post to be more clear.
Recall the filter between the AI and the world. The AI doesn’t directly say “yes/no.” The AI gives a proof to the filter which then says either “yes, the AI found a proof” or “no, the AI didn’t.” So they do all say ‘yes’ if they can. I will modify the post to be more clear.